From ce9c003089da945f97f06051607bd03e1b8f9c7e Mon Sep 17 00:00:00 2001
From: crystal20277 <jw123456>
Date: Thu, 8 Sep 2022 11:05:31 +0800
Subject: [PATCH] =?UTF-8?q?=E5=B0=86=E7=94=A8=E6=88=B7=E6=B4=BB=E8=B7=83?=
 =?UTF-8?q?=E5=BA=A6=E6=95=B0=E6=8D=AE=E4=BF=9D=E5=AD=98=E5=88=B0=E6=95=B0?=
 =?UTF-8?q?=E6=8D=AE=E5=BA=93?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 sql/01_2022-08-09.sql                               | 13 ++++++++++++-
 .../activity_analysis/data_process.py               | 13 +++++++++++++
 user_portrait_analysis/activity_analysis/train.py   | 11 +++++++----
 3 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/sql/01_2022-08-09.sql b/sql/01_2022-08-09.sql
index c91e540..119bd16 100644
--- a/sql/01_2022-08-09.sql
+++ b/sql/01_2022-08-09.sql
@@ -96,4 +96,15 @@ CREATE TABLE "public"."ai_repo_topic_detail" (
   "topic_id" int4,
   "topic_name" varchar(255) COLLATE "pg_catalog"."default",
   "created_unix" int8
-);
\ No newline at end of file
+);
+
+
+
+CREATE TABLE "public"."ai_user_activity" (
+    "user_id" int8,
+    "activity" int4,
+    "type" varchar(20) COLLATE "pg_catalog"."default",
+    "created_unix" int8
+  );
+
+
diff --git a/user_portrait_analysis/activity_analysis/data_process.py b/user_portrait_analysis/activity_analysis/data_process.py
index 239d6d0..4775a66 100644
--- a/user_portrait_analysis/activity_analysis/data_process.py
+++ b/user_portrait_analysis/activity_analysis/data_process.py
@@ -87,6 +87,19 @@ def get_rfm_data():
     return df_rfm
 
 
+def save_train_result_to_pgsql(df):
+    start = datetime.datetime.now()
+    logger.info("开始将用户活跃度数据保存到数据库...")
+
+    engine = create_engine(f'postgresql+psycopg2://{user}:{passwd}@{host}:{port}/{database}', pool_recycle=3600)
+    conn = engine.connect()
+
+    df['type'] = 'activity'
+    df['created_unix'] = int(datetime.datetime.now().timestamp())
+    df.to_sql('ai_user_activity', conn, index=False, if_exists='replace')
+    logger.info("用户活跃度数据保存到数据库完毕，共" + str(df.shape[0]) + "条数据，总耗时" + str((datetime.datetime.now() - start).seconds) + "秒")
+
+
 if __name__ == '__main__':
     # 取之前多少天登录的数据
     latest_data_date = get_before_date(data_before_days)
diff --git a/user_portrait_analysis/activity_analysis/train.py b/user_portrait_analysis/activity_analysis/train.py
index 36cb01d..4baf3dc 100644
--- a/user_portrait_analysis/activity_analysis/train.py
+++ b/user_portrait_analysis/activity_analysis/train.py
@@ -4,7 +4,7 @@ import pandas as pd
 from sklearn.cluster import KMeans
 from config import logger
 from config import RANDOM_SEED
-from data_process import get_rfm_data
+from data_process import get_rfm_data, save_train_result_to_pgsql
 from config import activity_analysis_path
 warnings.filterwarnings('ignore')
 
@@ -68,14 +68,17 @@ def train():
     # 将用户 id 和活跃度分值提取出来并创新建立一个表     
     result_csv['user_id'] = result_csv['user_id'].astype(int)
     result_csv['activity'] = result_csv['activity'].astype(int)
-    resuts_dict = dict(zip(result_csv['user_id'], result_csv['activity']))
+    result_dict = dict(zip(result_csv['user_id'], result_csv['activity']))
+
+    # 将训练结果保存到数据库
+    save_train_result_to_pgsql(result_csv)
 
     # 保存模型和结果
     pickle.dump(kmeans_model, open(activity_analysis_path + 'results/user_activity_model.pkl', 'wb'))
-    pickle.dump(resuts_dict, open(activity_analysis_path + 'results/user_activity_dict.pkl', 'wb'))
+    pickle.dump(result_dict, open(activity_analysis_path + 'results/user_activity_dict.pkl', 'wb'))
 
     logger.info('用户活跃度分析模型训练完成')
-    return resuts_dict
+    return result_dict
 
 
 if __name__ == '__main__':